English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Zendy Plus

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Zendy Tools

Zendy Open

Generative Adversarial Networks (GANs) have gained a lot of attention frommachine learning community due to their ability to learn and mimic an inputdata distribution. GANs consist of a discriminator and a generator working intandem playing a min-max game to learn a target underlying data distribution;when fed with data-points sampled from a simpler distribution (like uniform orGaussian distribution). Once trained, they allow synthetic generation ofexamples sampled from the target distribution. We investigate the applicationof GANs to generate synthetic feature vectors used for speech emotionrecognition. Specifically, we investigate two set ups: (i) a vanilla GAN thatlearns the distribution of a lower dimensional representation of the actualhigher dimensional feature vector and, (ii) a conditional GAN that learns thedistribution of the higher dimensional feature vectors conditioned on thelabels or the emotional class to which it belongs. As a potential practicalapplication of these synthetically generated samples, we measure anyimprovement in a classifier's performance when the synthetic data is used alongwith real data for training. We perform cross-validation analyses followed by across-corpus study.

On Enhancing Speech Emotion Recognition using Generative Adversarial Networks